Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A vehicle comprising: a user interface including a display and a speaker; a camera configured to capture an image of a passenger; a sensing device configured to measure bio-signals of the passenger; and a processor configured to: obtain emotion information representing emotion of the passenger based on the image; determine a content corresponding to the emotion information; control the user interface to output the determined content; obtain circumstance information representing circumstances of the passenger based on the image after the determined content is output; modify the determined content based on the circumstance information; and control the user interface to output the modified content, wherein the processor is further configured to: obtain the emotion information based on the image or the bio-signals of the passenger; and obtain the circumstance information based on the image or the bio-signals of the passenger after the determined content is output, and wherein the processor is further configured to compare at least one of the image with physical information by age to determine an age of the passenger, wherein the physical information comprises heart rate information.
2. The vehicle according to claim 1 , wherein the processor is further configured to: obtain the circumstance information based on the captured image or the measured bio-signals for a predetermined time after the determined content is output; and modify the determined content when a circumstance represented by the circumstance information corresponds to a predetermined circumstance.
3. The vehicle according to claim 2 , wherein the predetermined circumstance comprises at least one of a circumstance in which a degree of negativity of the emotion of the passenger represented by the emotion information is equal to or greater than a threshold level, a circumstance in which the passenger utters crying, a circumstance in which the passenger utters a protection request word, or a circumstance in which the passenger is sleepy.
This invention relates to vehicle systems designed to detect and respond to passenger emotions, particularly negative emotional states. The system monitors passenger emotions using sensors and determines when a predetermined negative emotional circumstance occurs. These circumstances include when the detected emotion's negativity exceeds a threshold level, when the passenger cries, when the passenger utters a protection request word, or when the passenger appears sleepy. Upon detecting such a circumstance, the system triggers a response to address the passenger's emotional state. The vehicle may include a sensor system to detect passenger emotions, such as facial expressions, vocal patterns, or physiological signals, and a processing unit to analyze this data. The system may also include a response mechanism, such as adjusting vehicle conditions, providing verbal reassurance, or contacting emergency services. The invention aims to enhance passenger safety and comfort by proactively responding to distress or vulnerability.
4. The vehicle according to claim 2 , wherein the processor is further configured to modify at least one of a playback speed, playback music, a playback interval, an output size, a movement of a character, a shape of the character, a color of the character, a face of the character, or a voice of the character of the determined content.
5. The vehicle according to claim 4 , wherein the processor is further configured to: determine the playback interval, in which a degree of positivity of the emotion of the passenger is less than a threshold level among at least one playback interval of the determined content, based on the emotion information; and modify the determined content to increase the playback speed of the playback interval.
6. The vehicle according to claim 4 , wherein the processor is further configured to determine the playback interval, in which a degree of positivity of the emotion of the passenger is less than a threshold level among at least one playback interval of the determined content, based on the emotion information.
7. The vehicle according to claim 6 , wherein the processor is further configured to modify the determined content to play so that the playback music or the playback image in the playback interval is repeatedly played.
8. The vehicle according to claim 6 , wherein the processor is further configured to: modify the determined content to increase the output size of the playback music in the playback interval; or modify the determined content to increase an image size of the playback image in the playback interval.
9. The vehicle according to claim 6 , wherein the processor is further configured to modify the determined content so that the movement of the character, the shape of the character, or the color of the character in the playback interval is reflected in the character of a current playback interval.
10. The vehicle according to claim 4 , wherein the processor is further configured to modify the determined content so that the face of the character is modified into a face of the passenger or a face of a guardian, or the voice of the character is modified into a voice of the passenger or a voice of the guardian.
11. The vehicle according to claim 1 , wherein the processor is further configured to: determine an age corresponding content group that includes at least one content corresponding to the age; and determine the content having a highest association with the emotion represented by the emotion information among the at least one content included in the age corresponding content group as the content corresponding to the emotion information.
12. The vehicle according to claim 11 , wherein the processor is further configured to: obtain the emotion information for a predetermined time after the determined content is output based on the image captured or the bio-signals measured for the predetermined time after the determined content is output; compare the emotion information for the predetermined time after the determined content is output and the emotion information prior to an output of the determined content; and update an association between the emotion represented by the emotion information and the determined content.
13. The vehicle according to claim 12 , wherein the processor is further configured to: increase, when a degree of positivity of the emotion information for the predetermined time after the output of the determined content is greater than the degree of positivity of the emotion information prior to the output of the determined content, the association between the determined content and the emotion represented by the emotion information; decrease, when a degree of positivity of the emotion information for the predetermined time after the output of the determined content is lower than the degree of positivity of the emotion information prior to the output of the determined content, the association between the determined content and the emotion represented by the emotion information; and determine, when the association of the emotion represented by the emotion information of the determined content is lower than the association of the emotion represented by the emotion information of the other contents including the age corresponding content group, the other contents as the content corresponding to the emotion information.
14. A method of controlling a vehicle that includes a user interface including a display and a speaker, the method comprising: capturing, by a camera, an image of the passenger; measuring, by a sensing device, bio-signals of the passenger; obtaining, by a processor, emotion information representing emotion of the passenger based on the image; determining, by the processor, content corresponding to the emotion information; controlling, by the processor, the user interface to output the determined content; obtaining, by the processor, circumstance information representing circumstances of the passenger based on the image after the determined content is output; modifying, by the processor, the determined content based on the circumstance information; controlling, by the processor, the user interface to output the modified content; obtaining, by the processor, the emotion information based on the image or the bio-signals; obtaining, by the processor, the circumstance information based on the image or the bio-signals after the determined content is output; and comparing, by the processor, at least one of the image with physical information by age to determine an age of the passenger, wherein the physical information comprises heart rate information.
15. The method according to claim 14 , wherein the modifying of the determined content comprises: obtaining the circumstance information based on the captured image or the measured bio-signals for a predetermined time after the determined content is output; and modifying the determined content when a circumstance represented by the circumstance information corresponds to a predetermined circumstance.
16. The method according to claim 15 , wherein the predetermined circumstance comprises at least one of a circumstance in which a degree of negativity of the emotion of the passenger represented by the emotion information is equal to or greater than a threshold level, a circumstance in which the passenger utters crying, a circumstance in which the passenger utters a protection request word, or a circumstance in which the passenger is sleepy.
17. The method according to claim 15 , wherein the modifying of the determined content comprises: modifying at least one of a playback speed, playback music, a playback interval, an output size, a movement of a character, a shape of the character, a color of the character, a face of the character, or a voice of the character of the determined content.
This invention relates to modifying digital content, particularly multimedia content such as videos, animations, or interactive media, to enhance user engagement or adapt to specific preferences. The core problem addressed is the static nature of traditional digital content, which lacks dynamic adjustments to suit individual user needs or environmental conditions. The solution involves analyzing user data, such as preferences, behavior, or environmental factors, to determine the most suitable content for presentation. Once the content is selected, the system modifies various attributes to optimize the user experience. These modifications include adjusting playback speed, music, intervals, output size, character movements, shapes, colors, facial expressions, or voice characteristics. For example, a video may be sped up for a user who prefers faster pacing, or a character's appearance may be altered to better match cultural preferences. The modifications are applied in real-time or pre-processed to ensure seamless delivery. This approach enhances personalization, accessibility, and adaptability in digital media consumption.
18. The method according to claim 17 , wherein the modifying of the determined content comprises: determining the playback interval, in which a degree of positivity of the emotion of the passenger is less than a threshold level among at least one playback interval of the determined content, based on the emotion information; and modifying the determined content to increase the playback speed of the playback interval.
19. The method according to claim 17 , wherein the modifying of the determined content comprises: determining the playback interval in which a degree of positivity of the emotion of the passenger is less than a threshold level among at least one playback interval of the determined content, based on the emotion information.
20. The method according to claim 19 , wherein the modifying of the determined content comprises: modifying the determined content to play so that the playback music or the playback image in the first playback interval is repeatedly played.
21. The method according to claim 19 , wherein the modifying of the determined content comprises: modifying the determined content to increase the output size of the playback music in the playback interval; or modifying the determined content to increase an image size of the playback image in the playback interval.
22. The method according to claim 19 , wherein the modifying of the determined content comprises: modifying the determined content so that the movement of the character, the shape of the character, or the color of the character in the first playback interval is reflected in the character of a current playback interval.
23. The method according to claim 17 , wherein the modifying of the determined content comprises: modifying the determined content so that the face of the character is modified into a face of the passenger or a face of a guardian, or the voice of the character is modified into a voice of the passenger or a voice of the guardian.
24. The method according to claim 14 , wherein the determining of the content corresponding to the emotion information comprises: determining an age corresponding content group that includes at least one content corresponding to the age; and determining the content having a highest association with the emotion represented by the emotion information among the at least one content included in the age corresponding content group as the content corresponding to the emotion information.
25. The method according to claim 24 , further comprising: obtaining, by the processor, the emotion information for the predetermined time after the determined content is output based on the image captured or the bio-signals measured for the predetermined time after the determined content is output; comparing, by the processor, the emotion information for the predetermined time after the determined content is output and the emotion information prior to the output of the determined content; and updating, by the processor, the association between the emotion represented by the emotion information and the determined content.
26. The method according to claim 25 , wherein the updating of the association comprises: increasing, when a degree of positivity of the emotion information for the predetermined time after the output of the determined content is greater than the degree of positivity of the emotion information prior to the output of the determined content, an association between the determined content and the emotion represented by the emotion information; decreasing, when a degree of positivity of the emotion information for the predetermined time after the output of the determined content is lower than the degree of positivity of the emotion information prior to the output of the determined content, the association between the determined content and the emotion represented by the emotion information; and determining, by the processor, when the association of the emotion represented by the emotion information of the determined content is lower than the association of the emotion represented by the emotion information of the other contents including the age corresponding content group, the other contents as the content corresponding to the emotion information.
This invention relates to a system for dynamically adjusting content recommendations based on user emotional responses. The system monitors a user's emotional state, represented by emotion information, before and after presenting content to determine the impact of the content on the user's emotions. If the user's emotional positivity increases after content is presented, the system strengthens the association between that content and the corresponding emotion. Conversely, if the user's emotional positivity decreases, the system weakens the association. The system then compares the strength of these associations across different content, including age-appropriate content groups, to select the most emotionally suitable content for future recommendations. This adaptive approach ensures that content recommendations align with the user's emotional preferences over time, improving personalization and user satisfaction. The system leverages real-time emotional feedback to refine content selection, making it particularly useful in applications like entertainment, education, or mental health support where emotional engagement is critical.
Unknown
February 9, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.